Summary of the paper
| Title | Meaning Representation: From Continuity to Discreteness |
|---|---|
| Authors | Fabienne Venant |
| Abstract | This paper presents a geometric approach to meaning representation within theframework of continuous mathematics. Meaning representation is a central issuein Natural Language Processing, in particular for tasks like word sensedisambiguation or information extraction. We want here to discuss the relevanceof using continuous models in semantics. We don’t want to argue thecontinuous or discrete nature of lexical meaning. We use continuity as a toolto access and manipulate lexical meaning. Following Victorri (1994), we assumethat continuity or discreteness are not properties of phenomena butcharacterizations of theories upon phenomena. We briefly describe ourtheoretical framework, the dynamical construction of meaning (Victorri andFuchs, 1996), then present the way we automatically build continuous semanticspaces from a graph of synonymy and discuss their relevance and utility. Wealso think that discreteness and continuity can collaborate. We show here howwe can complete our geometric representations with informations from discretedescriptions of meaning. |
| Language | Knowledge Discovery/Representation |
| Topics | Lexicon, lexical database, Word Sense Disambiguation, Knowledge Discovery/Representation |
Full paper  |
Meaning Representation: From Continuity to Discreteness |
| Bibtex | @InProceedings{VENANT10.207, author = {Fabienne Venant}, title = {Meaning Representation: From Continuity to Discreteness}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |